View allAll Photos Tagged dall-e
So you may or not have heard about 'Dall-e' - the uncanny Artificially Intelligent image tool that can create photo-real, painterly or illustrative images entirely from text prompts, limited only by your imagination.
Frankly - it's a amazing and scary in equal parts.
This is an attempt to turn an image I got it to create from a prompt into a LEGO build - sort of a proof of concept based on the idea that if I have no creative mojo for an idea, then I can let a computer do the dreaming, then i can build something based / influenced on it.
This is a moon rover based on the prompt "biomechanical retro moon truck - digital art"
Not sure it nailed the 'biomech' part (it did in other attempts, but was too spindly to realise in Lego) but it very much felt like the sort of moon truck I like to build and yet not, and yet, completely original and outside of the usual influences of being in the AFOL bubble—so that is what I have done!
Is this the first ever Lego built solely inspired by the dreams of an AI prototype?
Maybe?....
(Alternative pics from other angles, along with the original sketch in the comments / gallery)
See my albums list for some of my best work: www.flickr.com/photos/200044612@N04/albums/
See my main account for my photography, videos, fractal images and more here: www.flickr.com/photos/josh-rokman/
Made with Image Creator from Microsoft Designer, formerly known as the Bing Image Creator. Powered by DALL·E 3.
I think that AI image generation is similar in many ways to photography. The camera itself handles all the fine details, but the photographer is in charge of curating the types of images that will be created.
Ultimately, it is all about maximizing the probability that something good will be created.
This is very similar to AI image generation, in terms of the skills involved and what the human does vs. what the machine does.
You can't compare AI image generation to the process of actually making these images from scratch with 3D software or paint/pencils, where the human controls every detail.
However, I think the process really is very similar to that of photography, as I made the case for above. I think that DALL-E 3 is by far the most powerful AI image generation tool currently available.
- Josh
See my albums list for some of my best work: www.flickr.com/photos/200044612@N04/albums/
See my main account for my photography, videos, fractal images and more here: www.flickr.com/photos/josh-rokman/
Made with Image Creator from Microsoft Designer, formerly known as the Bing Image Creator. Powered by DALL·E 3.
I think that AI image generation is similar in many ways to photography. The camera itself handles all the fine details, but the photographer is in charge of curating the types of images that will be created.
Ultimately, it is all about maximizing the probability that something good will be created.
This is very similar to AI image generation, in terms of the skills involved and what the human does vs. what the machine does.
You can't compare AI image generation to the process of actually making these images from scratch with 3D software or paint/pencils, where the human controls every detail.
However, I think the process really is very similar to that of photography, as I made the case for above. I think that DALL-E 3 is by far the most powerful AI image generation tool currently available.
- Josh